You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2021/01/12 20:10:52 UTC
[tika] branch main updated: TIKA-3267 change boolean getXYZ to
boolean isXYZ
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 5ad435d TIKA-3267 change boolean getXYZ to boolean isXYZ
5ad435d is described below
commit 5ad435d39e39558b98af3af5aca291eef22651f0
Author: tallison <ta...@apache.org>
AuthorDate: Tue Jan 12 15:10:23 2021 -0500
TIKA-3267 change boolean getXYZ to boolean isXYZ
---
.../apache/tika/batch/BatchProcessDriverCLI.java | 2 +-
.../java/org/apache/tika/batch/ParserFactory.java | 2 +-
.../org/apache/tika/batch/fs/BatchDriverTest.java | 12 +--
.../sax/EndDocumentShieldingContentHandler.java | 2 +-
.../org/apache/tika/parser/crypto/TSDParser.java | 6 +-
.../org/apache/tika/parser/html/HtmlParser.java | 2 +-
.../parser/microsoft/AbstractOfficeParser.java | 30 +++---
.../tika/parser/microsoft/ExcelExtractor.java | 12 +--
.../tika/parser/microsoft/HSLFExtractor.java | 19 ++--
.../apache/tika/parser/microsoft/OfficeParser.java | 2 +-
.../tika/parser/microsoft/OfficeParserConfig.java | 24 ++---
.../tika/parser/microsoft/OutlookExtractor.java | 2 +-
.../tika/parser/microsoft/WordExtractor.java | 8 +-
.../microsoft/ooxml/AbstractOOXMLExtractor.java | 3 +-
.../microsoft/ooxml/OOXMLExtractorFactory.java | 4 +-
.../microsoft/ooxml/OOXMLTikaBodyPartHandler.java | 8 +-
.../ooxml/OOXMLWordAndPowerPointTextHandler.java | 11 +-
.../ooxml/POIXMLTextExtractorDecorator.java | 2 +-
.../ooxml/SXSLFPowerPointExtractorDecorator.java | 10 +-
.../ooxml/SXWPFWordExtractorDecorator.java | 8 +-
.../ooxml/XSLFPowerPointExtractorDecorator.java | 8 +-
.../ooxml/XSSFExcelExtractorDecorator.java | 10 +-
.../ooxml/XWPFWordExtractorDecorator.java | 12 +--
.../xslf/XSLFEventBasedPowerPointExtractor.java | 4 +-
.../ooxml/xwpf/XWPFEventBasedWordExtractor.java | 4 +-
.../java/org/apache/tika/parser/mif/MIFParser.java | 2 +-
.../apache/tika/parser/odf/OpenDocumentParser.java | 2 +-
.../apache/tika/parser/ocr/ImagePreprocessor.java | 2 +-
.../apache/tika/parser/ocr/TesseractOCRConfig.java | 11 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 4 +-
.../tika/parser/ocr/TesseractOCRConfigTest.java | 6 +-
.../tika/parser/ocr/TesseractOCRParserTest.java | 4 +-
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 12 +--
.../tika/parser/pdf/ImageGraphicsEngine.java | 10 +-
.../java/org/apache/tika/parser/pdf/PDF2XHTML.java | 10 +-
.../java/org/apache/tika/parser/pdf/PDFParser.java | 22 ++--
.../apache/tika/parser/pdf/PDFParserConfig.java | 112 ++++++++++-----------
.../org/apache/tika/parser/pdf/PDFParserTest.java | 11 +-
.../tika/parser/txt/Icu4jEncodingDetector.java | 2 +-
.../org/apache/tika/parser/xliff/XLZParser.java | 2 +-
.../tika/config/TikaEncodingDetectorTest.java | 2 +-
41 files changed, 196 insertions(+), 225 deletions(-)
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java b/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java
index 35cfc08..a1d4050 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java
@@ -203,7 +203,7 @@ public class BatchProcessDriverCLI {
return numRestarts;
}
- public boolean getUserInterrupted() {
+ public boolean isUserInterrupted() {
return userInterrupted;
}
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java b/tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java
index 6908a17..d8c69f9 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java
@@ -26,7 +26,7 @@ public abstract class ParserFactory {
public abstract Parser getParser(TikaConfig config);
- public boolean getParseRecursively() {
+ public boolean isParseRecursively() {
return parseRecursively;
}
diff --git a/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchDriverTest.java b/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchDriverTest.java
index 57e56f5..7a77c14 100644
--- a/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchDriverTest.java
+++ b/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchDriverTest.java
@@ -49,7 +49,7 @@ public class BatchDriverTest extends FSBatchTestBase {
driver.execute();
assertEquals(0, driver.getNumRestarts());
- assertFalse(driver.getUserInterrupted());
+ assertFalse(driver.isUserInterrupted());
assertEquals(5, countChildren(outputDir));
assertContains("first test file",
@@ -69,7 +69,7 @@ public class BatchDriverTest extends FSBatchTestBase {
driver.execute();
//could be one or two depending on timing
assertTrue(driver.getNumRestarts() > 0);
- assertFalse(driver.getUserInterrupted());
+ assertFalse(driver.isUserInterrupted());
assertContains("first test file",
readFileToString(outputDir.resolve("test6_ok.xml.xml"), UTF_8));
}
@@ -89,7 +89,7 @@ public class BatchDriverTest extends FSBatchTestBase {
BatchProcessDriverCLI driver = getNewDriver("/tika-batch-config-test.xml", mod);
driver.execute();
assertEquals(0, driver.getNumRestarts());
- assertFalse(driver.getUserInterrupted());
+ assertFalse(driver.isUserInterrupted());
assertEquals(2, countChildren(outputDir));
Path test2 = outputDir.resolve("test2_norestart.xml.xml");
assertTrue("test2_norestart.xml", Files.exists(test2));
@@ -109,7 +109,7 @@ public class BatchDriverTest extends FSBatchTestBase {
BatchProcessDriverCLI driver = getNewDriver("/tika-batch-config-test.xml", args);
driver.execute();
assertEquals(1, driver.getNumRestarts());
- assertFalse(driver.getUserInterrupted());
+ assertFalse(driver.isUserInterrupted());
assertContains("first test file",
readFileToString(outputDir.resolve("test2_ok.xml.xml"), UTF_8));
}
@@ -127,7 +127,7 @@ public class BatchDriverTest extends FSBatchTestBase {
BatchProcessDriverCLI driver = getNewDriver("/tika-batch-config-test.xml", commandLine);
driver.execute();
assertEquals(3, driver.getNumRestarts());
- assertFalse(driver.getUserInterrupted());
+ assertFalse(driver.isUserInterrupted());
assertContains("first test file",
readFileToString(outputDir.resolve("test6_ok.xml.xml"), UTF_8));
}
@@ -149,7 +149,7 @@ public class BatchDriverTest extends FSBatchTestBase {
BatchProcessDriverCLI driver = getNewDriver("/tika-batch-config-test.xml", commandLine);
driver.execute();
assertEquals(2, driver.getNumRestarts());
- assertFalse(driver.getUserInterrupted());
+ assertFalse(driver.isUserInterrupted());
assertEquals(3, countChildren(outputDir));
}
diff --git a/tika-core/src/main/java/org/apache/tika/sax/EndDocumentShieldingContentHandler.java b/tika-core/src/main/java/org/apache/tika/sax/EndDocumentShieldingContentHandler.java
index 8c91ad3..03325ed 100644
--- a/tika-core/src/main/java/org/apache/tika/sax/EndDocumentShieldingContentHandler.java
+++ b/tika-core/src/main/java/org/apache/tika/sax/EndDocumentShieldingContentHandler.java
@@ -47,7 +47,7 @@ public class EndDocumentShieldingContentHandler extends ContentHandlerDecorator
super.endDocument();
}
- public boolean getEndDocumentWasCalled() {
+ public boolean isEndDocumentWasCalled() {
return endDocumentCalled;
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
index 1b48ccb..f2ae7a6 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
@@ -215,13 +215,13 @@ public class TSDParser extends AbstractParser {
this.algorithm = algorithm;
}
- public Boolean getParseBuilt() {
+ public Boolean isParseBuilt() {
return parseBuilt;
}
public String getParseBuiltStr() {
- return String.valueOf(this.getParseBuilt() != null ?
- this.getParseBuilt() : false);
+ return String.valueOf(this.isParseBuilt() != null ?
+ this.isParseBuilt() : false);
}
public void setParseBuilt(Boolean parseBuilt) {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlParser.java
index adf591a..ed01db5 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlParser.java
@@ -240,7 +240,7 @@ public class HtmlParser extends AbstractEncodingDetectorParser {
this.extractScripts = extractScripts;
}
- public boolean getExtractScripts() {
+ public boolean isExtractScripts() {
return extractScripts;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java
index 3c51afa..2b22b4b 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java
@@ -40,39 +40,39 @@ public abstract class AbstractOfficeParser extends AbstractParser {
}
/**
- * @see OfficeParserConfig#getIncludeDeletedContent
+ * @see OfficeParserConfig#isIncludeDeletedContent
*
* @return
*/
- public boolean getIncludeDeletedContent() {
- return defaultOfficeParserConfig.getIncludeDeletedContent();
+ public boolean isIncludeDeletedContent() {
+ return defaultOfficeParserConfig.isIncludeDeletedContent();
}
/**
- * @see OfficeParserConfig#getIncludeMoveFromContent()
+ * @see OfficeParserConfig#isIncludeMoveFromContent()
*
* @return
*/
- public boolean getIncludeMoveFromContent() {
- return defaultOfficeParserConfig.getIncludeMoveFromContent();
+ public boolean isIncludeMoveFromContent() {
+ return defaultOfficeParserConfig.isIncludeMoveFromContent();
}
/**
- * @see OfficeParserConfig#getUseSAXDocxExtractor()
+ * @see OfficeParserConfig#isUseSAXDocxExtractor()
*
* @return
*/
- public boolean getUseSAXDocxExtractor() {
- return defaultOfficeParserConfig.getUseSAXDocxExtractor();
+ public boolean isUseSAXDocxExtractor() {
+ return defaultOfficeParserConfig.isUseSAXDocxExtractor();
}
/**
- * @see OfficeParserConfig#getExtractMacros()
+ * @see OfficeParserConfig#isExtractMacros()
* @return whether or not to extract macros
*/
- public boolean getExtractMacros() {
- return defaultOfficeParserConfig.getExtractMacros();
+ public boolean isExtractMacros() {
+ return defaultOfficeParserConfig.isExtractMacros();
}
@Field
@@ -111,7 +111,7 @@ public abstract class AbstractOfficeParser extends AbstractParser {
}
void getConcatenatePhoneticRuns() {
- defaultOfficeParserConfig.getConcatenatePhoneticRuns();
+ defaultOfficeParserConfig.isConcatenatePhoneticRuns();
}
/**
@@ -129,8 +129,8 @@ public abstract class AbstractOfficeParser extends AbstractParser {
}
- public boolean getExtractAllAlternativesFromMSG() {
- return defaultOfficeParserConfig.getExtractAllAlternativesFromMSG();
+ public boolean isExtractAllAlternativesFromMSG() {
+ return defaultOfficeParserConfig.isExtractAllAlternativesFromMSG();
}
/**
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
index ddf6cd4..e731c0a 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
@@ -329,7 +329,7 @@ public class ExcelExtractor extends AbstractPOIFSExtractor {
hssfRequest.addListener(formatListener, FormatRecord.sid);
hssfRequest.addListener(formatListener, ExtendedFormatRecord.sid);
hssfRequest.addListener(formatListener, DrawingGroupRecord.sid);
- if (extractor.officeParserConfig.getIncludeHeadersAndFooters()) {
+ if (extractor.officeParserConfig.isIncludeHeadersAndFooters()) {
hssfRequest.addListener(formatListener, HeaderRecord.sid);
hssfRequest.addListener(formatListener, FooterRecord.sid);
}
@@ -456,7 +456,7 @@ public class ExcelExtractor extends AbstractPOIFSExtractor {
LabelSSTRecord sst = (LabelSSTRecord) record;
UnicodeString unicode = sstRecord.getString(sst.getSSTIndex());
String cellString = null;
- if (officeParserConfig.getConcatenatePhoneticRuns()) {
+ if (officeParserConfig.isConcatenatePhoneticRuns()) {
String phonetic = (unicode != null
&& unicode.getExtendedRst() != null
&& unicode.getExtendedRst().getPhoneticText() != null
@@ -497,7 +497,7 @@ public class ExcelExtractor extends AbstractPOIFSExtractor {
break;
case TextObjectRecord.sid:
- if (extractor.officeParserConfig.getIncludeShapeBasedContent()) {
+ if (extractor.officeParserConfig.isIncludeShapeBasedContent()) {
TextObjectRecord tor = (TextObjectRecord) record;
addTextCell(record, tor.getStr().getString());
}
@@ -515,14 +515,14 @@ public class ExcelExtractor extends AbstractPOIFSExtractor {
break;
case HeaderRecord.sid:
- if (extractor.officeParserConfig.getIncludeHeadersAndFooters()) {
+ if (extractor.officeParserConfig.isIncludeHeadersAndFooters()) {
HeaderRecord headerRecord = (HeaderRecord) record;
addTextCell(record, headerRecord.getText());
}
break;
case FooterRecord.sid:
- if (extractor.officeParserConfig.getIncludeHeadersAndFooters()) {
+ if (extractor.officeParserConfig.isIncludeHeadersAndFooters()) {
FooterRecord footerRecord = (FooterRecord) record;
addTextCell(record, footerRecord.getText());
}
@@ -631,7 +631,7 @@ public class ExcelExtractor extends AbstractPOIFSExtractor {
handler.startElement("tr");
handler.startElement("td");
currentRow++;
- } while (officeParserConfig.getIncludeMissingRows() &&
+ } while (officeParserConfig.isIncludeMissingRows() &&
currentRow < entry.getKey().y);
currentRow = entry.getKey().y;
currentColumn = 0;
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
index 79fa38c..b77d292 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
@@ -44,7 +44,6 @@ import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.sl.usermodel.Comment;
import org.apache.poi.sl.usermodel.ShapeContainer;
import org.apache.poi.sl.usermodel.SimpleShape;
-import org.apache.poi.sl.usermodel.TextParagraph;
import org.apache.tika.exception.EncryptedDocumentException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
@@ -93,14 +92,14 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
for (HSLFSlide slide : _slides) {
xhtml.startElement("div", "class", "slide");
HeadersFooters slideHeaderFooters =
- (officeParserConfig.getIncludeHeadersAndFooters()) ?
+ (officeParserConfig.isIncludeHeadersAndFooters()) ?
slide.getHeadersFooters() : null;
HeadersFooters notesHeadersFooters =
- (officeParserConfig.getIncludeHeadersAndFooters()) ?
+ (officeParserConfig.isIncludeHeadersAndFooters()) ?
ss.getNotesHeadersFooters() : null;
- if (officeParserConfig.getIncludeHeadersAndFooters()) {
+ if (officeParserConfig.isIncludeHeadersAndFooters()) {
// Slide header, if present
if (slideHeaderFooters != null && slideHeaderFooters.isHeaderVisible() && slideHeaderFooters.getHeaderText() != null) {
xhtml.startElement("p", "class", "slide-header");
@@ -112,7 +111,7 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
}
// Slide master, if present
- if (officeParserConfig.getIncludeSlideMasterContent()) {
+ if (officeParserConfig.isIncludeSlideMasterContent()) {
extractMaster(xhtml, slide.getMasterSheet());
}
// Slide text
@@ -132,7 +131,7 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
//end slide content
xhtml.endElement("div");
- if (officeParserConfig.getIncludeHeadersAndFooters()) {
+ if (officeParserConfig.isIncludeHeadersAndFooters()) {
// Slide footer, if present
if (slideHeaderFooters != null && slideHeaderFooters.isFooterVisible() && slideHeaderFooters.getFooterText() != null) {
xhtml.startElement("p", "class", "slide-footer");
@@ -151,7 +150,7 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
}
handleSlideEmbeddedPictures(ss, xhtml);
- if (officeParserConfig.getExtractMacros()) {
+ if (officeParserConfig.isExtractMacros()) {
extractMacros(ss, xhtml);
}
// All slides done
@@ -199,7 +198,7 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
private void handleNotes(HSLFSlide slide,
HeadersFooters notesHeaderFooters, XHTMLContentHandler xhtml) throws SAXException, TikaException, IOException {
- if (!officeParserConfig.getIncludeSlideNotes()) {
+ if (!officeParserConfig.isIncludeSlideNotes()) {
return;
}
// Find the Notes for this slide and extract inline
@@ -211,7 +210,7 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
xhtml.startElement("div", "class", "notes");
// Repeat the Notes header, if set
- if (officeParserConfig.getIncludeHeadersAndFooters() &&
+ if (officeParserConfig.isIncludeHeadersAndFooters() &&
notesHeaderFooters != null &&
notesHeaderFooters.isHeaderVisible() &&
notesHeaderFooters.getHeaderText() != null) {
@@ -237,7 +236,7 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
xhtml.endElement("div");
// Repeat the Notes footer, if set
- if (officeParserConfig.getIncludeHeadersAndFooters() &&
+ if (officeParserConfig.isIncludeHeadersAndFooters() &&
notesHeaderFooters != null &&
notesHeaderFooters.isFooterVisible() &&
notesHeaderFooters.getFooterText() != null) {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
index dc03d33..43cecfa 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
@@ -132,7 +132,7 @@ public class OfficeParser extends AbstractOfficeParser {
parse(root, context, metadata, xhtml);
OfficeParserConfig officeParserConfig = context.get(OfficeParserConfig.class);
- if (officeParserConfig.getExtractMacros()) {
+ if (officeParserConfig.isExtractMacros()) {
//now try to get macros.
//Note that macros are handled separately for ppt in HSLFExtractor.
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParserConfig.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParserConfig.java
index 53498b1..9240172 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParserConfig.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParserConfig.java
@@ -52,7 +52,7 @@ public class OfficeParserConfig implements Serializable {
*
* @return whether or not to extract macros
*/
- public boolean getExtractMacros() {
+ public boolean isExtractMacros() {
return extractMacros;
}
/**
@@ -66,7 +66,7 @@ public class OfficeParserConfig implements Serializable {
this.includeDeletedContent = includeDeletedContent;
}
- public boolean getIncludeDeletedContent() {
+ public boolean isIncludeDeletedContent() {
return includeDeletedContent;
}
@@ -87,7 +87,7 @@ public class OfficeParserConfig implements Serializable {
this.includeMoveFromContent = includeMoveFromContent;
}
- public boolean getIncludeMoveFromContent() {
+ public boolean isIncludeMoveFromContent() {
return includeMoveFromContent;
}
@@ -105,7 +105,7 @@ public class OfficeParserConfig implements Serializable {
this.includeShapeBasedContent = includeShapeBasedContent;
}
- public boolean getIncludeShapeBasedContent() {
+ public boolean isIncludeShapeBasedContent() {
return includeShapeBasedContent;
}
@@ -122,10 +122,10 @@ public class OfficeParserConfig implements Serializable {
this.includeHeadersAndFooters = includeHeadersAndFooters;
}
- public boolean getIncludeHeadersAndFooters() {
+ public boolean isIncludeHeadersAndFooters() {
return includeHeadersAndFooters;
}
- public boolean getUseSAXDocxExtractor() {
+ public boolean isUseSAXDocxExtractor() {
return useSAXDocxExtractor;
}
@@ -153,12 +153,12 @@ public class OfficeParserConfig implements Serializable {
this.useSAXPptxExtractor = useSAXPptxExtractor;
}
- public boolean getUseSAXPptxExtractor() {
+ public boolean isUseSAXPptxExtractor() {
return useSAXPptxExtractor;
}
- public boolean getConcatenatePhoneticRuns() {
+ public boolean isConcatenatePhoneticRuns() {
return concatenatePhoneticRuns;
}
@@ -191,7 +191,7 @@ public class OfficeParserConfig implements Serializable {
this.extractAllAlternativesFromMSG = extractAllAlternativesFromMSG;
}
- public boolean getExtractAllAlternativesFromMSG() {
+ public boolean isExtractAllAlternativesFromMSG() {
return extractAllAlternativesFromMSG;
}
@@ -205,11 +205,11 @@ public class OfficeParserConfig implements Serializable {
this.includeMissingRows = includeMissingRows;
}
- public boolean getIncludeMissingRows() {
+ public boolean isIncludeMissingRows() {
return includeMissingRows;
}
- public boolean getIncludeSlideNotes() {
+ public boolean isIncludeSlideNotes() {
return includeSlideNotes;
}
@@ -230,7 +230,7 @@ public class OfficeParserConfig implements Serializable {
* @since 1.19.1
* @return whether or not to process content in slide masters
*/
- public boolean getIncludeSlideMasterContent() {
+ public boolean isIncludeSlideMasterContent() {
return includeSlideMasterContent;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
index 9e09bbe..a170b1f 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
@@ -133,7 +133,7 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
public OutlookExtractor(DirectoryNode root, ParseContext context) throws TikaException {
super(context);
this.parseContext = context;
- this.extractAllAlternatives = context.get(OfficeParserConfig.class).getExtractAllAlternativesFromMSG();
+ this.extractAllAlternatives = context.get(OfficeParserConfig.class).isExtractAllAlternativesFromMSG();
try {
this.msg = new MAPIMessage(root);
} catch (IOException e) {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
index 6b3d08c..cf347f9 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
@@ -173,7 +173,7 @@ public class WordExtractor extends AbstractPOIFSExtractor {
PicturesSource pictures = new PicturesSource(document);
HeaderStories headerFooter = null;
// Do any headers, if present
- if (officeParserConfig.getIncludeHeadersAndFooters()) {
+ if (officeParserConfig.isIncludeHeadersAndFooters()) {
headerFooter = new HeaderStories(document);
Range[] headers = new Range[]{headerFooter.getFirstHeaderSubrange(),
headerFooter.getEvenHeaderSubrange(), headerFooter.getOddHeaderSubrange()};
@@ -187,7 +187,7 @@ public class WordExtractor extends AbstractPOIFSExtractor {
i += handleParagraph(p, 0, r, document, FieldsDocumentPart.MAIN, pictures, pictureTable, listManager, xhtml);
}
- if (officeParserConfig.getIncludeShapeBasedContent()) {
+ if (officeParserConfig.isIncludeShapeBasedContent()) {
// Do everything else
for (String paragraph : wordExtractor.getMainTextboxText()) {
xhtml.element("p", paragraph);
@@ -206,7 +206,7 @@ public class WordExtractor extends AbstractPOIFSExtractor {
xhtml.element("p", paragraph);
}
- if (officeParserConfig.getIncludeHeadersAndFooters()) {
+ if (officeParserConfig.isIncludeHeadersAndFooters()) {
// Do any footers, if present
Range[] footers = new Range[]{headerFooter.getFirstFooterSubrange(),
headerFooter.getEvenFooterSubrange(), headerFooter.getOddFooterSubrange()};
@@ -609,7 +609,7 @@ public class WordExtractor extends AbstractPOIFSExtractor {
return true;
}
return !cr.isMarkedDeleted() ||
- (cr.isMarkedDeleted() && officeParserConfig.getIncludeDeletedContent());
+ (cr.isMarkedDeleted() && officeParserConfig.isIncludeDeletedContent());
}
public static class TagAndStyle {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
index 5e3341c..4660f29 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
@@ -29,7 +29,6 @@ import java.util.List;
import java.util.Map;
import java.util.Set;
-import org.apache.poi.extractor.POITextExtractor;
import org.apache.poi.ooxml.POIXMLDocument;
import org.apache.poi.ooxml.extractor.ExtractorFactory;
import org.apache.poi.ooxml.extractor.POIXMLTextExtractor;
@@ -422,7 +421,7 @@ public abstract class AbstractOOXMLExtractor implements OOXMLExtractor {
void handleMacros(PackagePart macroPart, ContentHandler handler) throws TikaException, SAXException {
OfficeParserConfig officeParserConfig = context.get(OfficeParserConfig.class);
- if (officeParserConfig.getExtractMacros()) {
+ if (officeParserConfig.isExtractMacros()) {
try (InputStream is = macroPart.getInputStream()) {
try (POIFSFileSystem poifs = new POIFSFileSystem(is)) {
//Macro reading exceptions are already swallowed here
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
index f0af25b..29dc41f 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
@@ -155,11 +155,11 @@ public class OOXMLExtractorFactory {
// This has already been set by OOXMLParser's call to configure()
// We can rely on this being non-null.
OfficeParserConfig config = context.get(OfficeParserConfig.class);
- if (config.getUseSAXDocxExtractor()) {
+ if (config.isUseSAXDocxExtractor()) {
poiExtractor = trySXWPF(pkg);
}
if (poiExtractor == null) {
- poiExtractor = tryXSLF(pkg, config.getUseSAXPptxExtractor());
+ poiExtractor = tryXSLF(pkg, config.isUseSAXPptxExtractor());
}
if (type.equals(OOXMLParser.XPS)) {
poiExtractor = new XPSTextExtractor(pkg);
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java
index dcf2556..ae17a5f 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java
@@ -74,8 +74,8 @@ public class OOXMLTikaBodyPartHandler implements OOXMLWordAndPowerPointTextHandl
this.xhtml = xhtml;
this.styles = styles;
this.listManager = listManager;
- this.includeDeletedText = parserConfig.getIncludeDeletedContent();
- this.includeMoveFromText = parserConfig.getIncludeMoveFromContent();
+ this.includeDeletedText = parserConfig.isIncludeDeletedContent();
+ this.includeMoveFromText = parserConfig.isIncludeMoveFromContent();
}
@Override
@@ -332,7 +332,7 @@ public class OOXMLTikaBodyPartHandler implements OOXMLWordAndPowerPointTextHandl
}
@Override
- public boolean getIncludeDeletedText() {
+ public boolean isIncludeDeletedText() {
return includeDeletedText;
}
@@ -363,7 +363,7 @@ public class OOXMLTikaBodyPartHandler implements OOXMLWordAndPowerPointTextHandl
}
@Override
- public boolean getIncludeMoveFromText() {
+ public boolean isIncludeMoveFromText() {
return includeMoveFromText;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
index f0ba265..b7a2436 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
@@ -22,7 +22,6 @@ import java.util.Date;
import java.util.Map;
import org.apache.poi.xwpf.usermodel.UnderlinePatterns;
-import org.apache.tika.parser.microsoft.OfficeParserConfig;
import org.apache.tika.utils.DateUtils;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
@@ -499,12 +498,12 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
}
if (editType.equals(EditType.MOVE_FROM) && inT) {
- if (bodyContentsHandler.getIncludeMoveFromText()) {
+ if (bodyContentsHandler.isIncludeMoveFromText()) {
appendToBuffer(ch, start, length);
}
} else if (inT) {
appendToBuffer(ch, start, length);
- } else if (bodyContentsHandler.getIncludeDeletedText() && editType.equals(EditType.DELETE)) {
+ } else if (bodyContentsHandler.isIncludeDeletedText() && editType.equals(EditType.DELETE)) {
appendToBuffer(ch, start, length);
} else if (inV) {
appendToBuffer(ch, start, length);
@@ -522,7 +521,7 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
if (inT) {
appendToBuffer(ch, start, length);
- } else if (bodyContentsHandler.getIncludeDeletedText() && inDelText) {
+ } else if (bodyContentsHandler.isIncludeDeletedText() && inDelText) {
appendToBuffer(ch, start, length);
}
}
@@ -570,13 +569,13 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
void endEditedSection();
- boolean getIncludeDeletedText();
+ boolean isIncludeDeletedText();
void footnoteReference(String id);
void endnoteReference(String id);
- boolean getIncludeMoveFromText();
+ boolean isIncludeMoveFromText();
void embeddedOLERef(String refId);
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
index 56d8a71..758b04a 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
@@ -32,7 +32,7 @@ public class POIXMLTextExtractorDecorator extends AbstractOOXMLExtractor {
super(context, extractor);
if (extractor instanceof XSSFExcelExtractor) {
- ((XSSFExcelExtractor)extractor).setIncludeTextBoxes(config.getIncludeShapeBasedContent());
+ ((XSSFExcelExtractor)extractor).setIncludeTextBoxes(config.isIncludeShapeBasedContent());
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java
index a56f8e1..2372e15 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java
@@ -50,8 +50,6 @@ import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
-import javax.xml.parsers.SAXParser;
-
/**
* SAX/Streaming pptx extractior
*/
@@ -122,7 +120,7 @@ public class SXSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
}
}
- if (config.getIncludeSlideMasterContent()) {
+ if (config.isIncludeSlideMasterContent()) {
handleGeneralTextContainingPart(XSLFRelation.SLIDE_MASTER.getRelation(),
"slide-master",
mainDocument,
@@ -197,7 +195,7 @@ public class SXSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
xhtml.endElement("div");
- if (config.getIncludeSlideMasterContent()) {
+ if (config.isIncludeSlideMasterContent()) {
handleGeneralTextContainingPart(XSLFRelation.SLIDE_LAYOUT.getRelation(),
"slide-master-content", slidePart,
metadata,
@@ -205,13 +203,13 @@ public class SXSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
new OOXMLTikaBodyPartHandler(xhtml), linkedRelationships))
);
}
- if (config.getIncludeSlideNotes()) {
+ if (config.isIncludeSlideNotes()) {
handleGeneralTextContainingPart(XSLFRelation.NOTES.getRelation(),
"slide-notes", slidePart,
metadata,
new OOXMLWordAndPowerPointTextHandler(
new OOXMLTikaBodyPartHandler(xhtml), linkedRelationships));
- if (config.getIncludeSlideMasterContent()) {
+ if (config.isIncludeSlideMasterContent()) {
handleGeneralTextContainingPart(XSLFRelation.NOTES_MASTER.getRelation(),
"slide-notes-master", slidePart,
metadata,
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java
index 57bbfeb..edad970 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java
@@ -48,8 +48,6 @@ import org.apache.tika.utils.XMLReaderUtils;
import org.apache.xmlbeans.XmlException;
import org.xml.sax.SAXException;
-import javax.xml.parsers.SAXParser;
-
/**
* This is an experimental, alternative extractor for docx files.
* This streams the main document content rather than loading the
@@ -136,7 +134,7 @@ public class SXWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
ExceptionUtils.getStackTrace(e));
}
- if (config.getIncludeHeadersAndFooters()) {
+ if (config.isIncludeHeadersAndFooters()) {
//headers
try {
PackageRelationshipCollection headersPRC = documentPart.getRelationshipsByType(XWPFRelation.HEADER.getRelation());
@@ -169,7 +167,7 @@ public class SXWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
XWPFRelation.ENDNOTE.getRelation(),
}) {
//skip footers if we shouldn't extract them
- if (! config.getIncludeHeadersAndFooters() &&
+ if (! config.isIncludeHeadersAndFooters() &&
rel.equals(XWPFRelation.FOOTER.getRelation())) {
continue;
}
@@ -198,7 +196,7 @@ public class SXWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
new OfflineContentHandler(new EmbeddedContentHandler(
new OOXMLWordAndPowerPointTextHandler(
new OOXMLTikaBodyPartHandler(xhtml, styles, listManager,
- config), linkedRelationships, config.getIncludeShapeBasedContent(), config.getConcatenatePhoneticRuns()))),
+ config), linkedRelationships, config.isIncludeShapeBasedContent(), config.isConcatenatePhoneticRuns()))),
context);
} catch (TikaException|IOException e) {
metadata.add(TikaCoreProperties.TIKA_META_EXCEPTION_WARNING,
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
index 2b7e5ce..5df0041 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
@@ -30,13 +30,11 @@ import org.apache.poi.openxml4j.opc.PackageRelationship;
import org.apache.poi.openxml4j.opc.PackageRelationshipCollection;
import org.apache.poi.openxml4j.opc.PackagingURIHelper;
import org.apache.poi.openxml4j.opc.TargetMode;
-import org.apache.poi.sl.extractor.SlideShowExtractor;
import org.apache.poi.sl.usermodel.Placeholder;
import org.apache.poi.xslf.extractor.XSLFPowerPointExtractor;
import org.apache.poi.xslf.usermodel.XMLSlideShow;
import org.apache.poi.xslf.usermodel.XSLFComment;
import org.apache.poi.xslf.usermodel.XSLFCommentAuthors;
-import org.apache.poi.xslf.usermodel.XSLFComments;
import org.apache.poi.xslf.usermodel.XSLFGraphicFrame;
import org.apache.poi.xslf.usermodel.XSLFGroupShape;
import org.apache.poi.xslf.usermodel.XSLFHyperlink;
@@ -110,7 +108,7 @@ public class XSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
extractContent(slide.getShapes(), false, xhtml, slideDesc);
xhtml.endElement("div");
- if (config.getIncludeSlideMasterContent()) {
+ if (config.isIncludeSlideMasterContent()) {
// slide layout which is the master sheet for this slide
xhtml.startElement("div", "class", "slide-master-content");
XSLFSlideLayout slideLayout = slide.getMasterSheet();
@@ -121,7 +119,7 @@ public class XSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
XSLFSheet slideMaster = slideLayout.getMasterSheet();
extractContent(slideMaster.getShapes(), true, xhtml, null);
}
- if (config.getIncludeSlideNotes()) {
+ if (config.isIncludeSlideNotes()) {
// notes (if present)
XSLFNotes slideNotes = slide.getNotes();
if (slideNotes != null) {
@@ -205,7 +203,7 @@ public class XSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
boolean inHyperlink = false;
for (XSLFTextParagraph p : txt.getTextParagraphs()) {
xhtml.startElement("p");
- if (! config.getIncludeHeadersAndFooters() && p.isHeaderOrFooter()) {
+ if (! config.isIncludeHeadersAndFooters() && p.isHeaderOrFooter()) {
continue;
}
for (XSLFTextRun run : p.getTextRuns()) {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
index 56a0f10..5f56eba 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
@@ -105,7 +105,7 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
}
protected void configureExtractor(POIXMLTextExtractor extractor, Locale locale) {
- ((XSSFEventBasedExcelExtractor)extractor).setIncludeTextBoxes(config.getIncludeShapeBasedContent());
+ ((XSSFEventBasedExcelExtractor)extractor).setIncludeTextBoxes(config.isIncludeShapeBasedContent());
((XSSFEventBasedExcelExtractor)extractor).setFormulasNotResults(false);
((XSSFEventBasedExcelExtractor)extractor).setLocale(locale);
//given that we load our own shared strings table, setting:
@@ -142,7 +142,7 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
styles = xssfReader.getStylesTable();
iter = (XSSFReader.SheetIterator) xssfReader.getSheetsData();
- strings = new ReadOnlySharedStringsTable(container, config.getConcatenatePhoneticRuns());
+ strings = new ReadOnlySharedStringsTable(container, config.isConcatenatePhoneticRuns());
} catch (InvalidFormatException e) {
throw new XmlException(e);
} catch (OpenXML4JException oe) {
@@ -184,7 +184,7 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
}
// Do text held in shapes, if required
- if (config.getIncludeShapeBasedContent()) {
+ if (config.isIncludeShapeBasedContent()) {
List<XSSFShape> shapes = iter.getShapes();
processShapes(shapes, xhtml);
}
@@ -413,8 +413,8 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
private int lastSeenCol = -1;
protected SheetTextAsHTML(OfficeParserConfig config, XHTMLContentHandler xhtml) {
- this.includeHeadersFooters = config.getIncludeHeadersAndFooters();
- this.includeMissingRows = config.getIncludeMissingRows();
+ this.includeHeadersFooters = config.isIncludeHeadersAndFooters();
+ this.includeMissingRows = config.isIncludeMissingRows();
this.xhtml = xhtml;
headers = new ArrayList<String>();
footers = new ArrayList<String>();
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
index 9ad3877..a41e3e7 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
@@ -116,7 +116,7 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
XWPFHeaderFooterPolicy hfPolicy = document.getHeaderFooterPolicy();
XWPFListManager listManager = new XWPFListManager(document.getNumbering());
// headers
- if (hfPolicy != null && config.getIncludeHeadersAndFooters()) {
+ if (hfPolicy != null && config.isIncludeHeadersAndFooters()) {
extractHeaders(xhtml, hfPolicy, listManager);
}
@@ -147,7 +147,7 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
);
// then all document footers
- if (hfPolicy != null && config.getIncludeHeadersAndFooters()) {
+ if (hfPolicy != null && config.isIncludeHeadersAndFooters()) {
extractFooters(xhtml, hfPolicy, listManager);
}
}
@@ -189,7 +189,7 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
XWPFHeaderFooterPolicy headerFooterPolicy = null;
if (paragraph.getCTP().getPPr() != null) {
CTSectPr ctSectPr = paragraph.getCTP().getPPr().getSectPr();
- if (ctSectPr != null && config.getIncludeHeadersAndFooters()) {
+ if (ctSectPr != null && config.isIncludeHeadersAndFooters()) {
headerFooterPolicy =
new XWPFHeaderFooterPolicy(document, ctSectPr);
extractHeaders(xhtml, headerFooterPolicy, listManager);
@@ -331,7 +331,7 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
// Also extract any paragraphs embedded in text boxes
//Note "w:txbxContent//"...must look for all descendant paragraphs
//not just the immediate children of txbxContent -- TIKA-2807
- if (config.getIncludeShapeBasedContent()) {
+ if (config.isIncludeShapeBasedContent()) {
for (XmlObject embeddedParagraph : paragraph.getCTP().selectPath("declare namespace w='http://schemas.openxmlformats.org/wordprocessingml/2006/main' declare namespace wps='http://schemas.microsoft.com/office/word/2010/wordprocessingShape' .//*/wps:txbx/w:txbxContent//w:p")) {
extractParagraph(new XWPFParagraph(CTP.Factory.parse(embeddedParagraph.xmlText()), paragraph.getBody()), listManager, xhtml);
}
@@ -340,7 +340,7 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
// Finish this paragraph
xhtml.endElement(tag);
- if (headerFooterPolicy != null && config.getIncludeHeadersAndFooters()) {
+ if (headerFooterPolicy != null && config.isIncludeHeadersAndFooters()) {
extractFooters(xhtml, headerFooterPolicy, listManager);
}
}
@@ -366,7 +366,7 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
// open/close required tags if run changes formatting
FormattingUtils.ensureFormattingState(xhtml, FormattingUtils.toTags(run), formattingState);
- if (config.getConcatenatePhoneticRuns()) {
+ if (config.isConcatenatePhoneticRuns()) {
xhtml.characters(run.toString());
} else {
xhtml.characters(run.text());
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xslf/XSLFEventBasedPowerPointExtractor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xslf/XSLFEventBasedPowerPointExtractor.java
index 76750ca..ec161cf 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xslf/XSLFEventBasedPowerPointExtractor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xslf/XSLFEventBasedPowerPointExtractor.java
@@ -169,7 +169,7 @@ public class XSLFEventBasedPowerPointExtractor extends POIXMLTextExtractor {
}
@Override
- public boolean getIncludeDeletedText() {
+ public boolean isIncludeDeletedText() {
return false;
}
@@ -184,7 +184,7 @@ public class XSLFEventBasedPowerPointExtractor extends POIXMLTextExtractor {
}
@Override
- public boolean getIncludeMoveFromText() {
+ public boolean isIncludeMoveFromText() {
return false;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xwpf/XWPFEventBasedWordExtractor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xwpf/XWPFEventBasedWordExtractor.java
index fef4e9e..4fd226e 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xwpf/XWPFEventBasedWordExtractor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xwpf/XWPFEventBasedWordExtractor.java
@@ -324,7 +324,7 @@ public class XWPFEventBasedWordExtractor extends POIXMLTextExtractor {
}
@Override
- public boolean getIncludeDeletedText() {
+ public boolean isIncludeDeletedText() {
return true;
}
@@ -339,7 +339,7 @@ public class XWPFEventBasedWordExtractor extends POIXMLTextExtractor {
}
@Override
- public boolean getIncludeMoveFromText() {
+ public boolean isIncludeMoveFromText() {
return false;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/mif/MIFParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/mif/MIFParser.java
index 2a44390..19d5eb5 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/mif/MIFParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/mif/MIFParser.java
@@ -77,7 +77,7 @@ public class MIFParser extends AbstractEncodingDetectorParser {
MIFExtractor.parse(reader, getContentHandler(parseHandler, metadata));
xhtml.endDocument();
- if (parseHandler.getEndDocumentWasCalled()) {
+ if (parseHandler.isEndDocumentWasCalled()) {
parseHandler.reallyEndDocument();
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
index b2e55ca..40b701d 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
@@ -176,7 +176,7 @@ public class OpenDocumentParser extends AbstractParser {
}
// Only now call the end document
- if (handler.getEndDocumentWasCalled()) {
+ if (handler.isEndDocumentWasCalled()) {
handler.reallyEndDocument();
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java
index 8ec3bad..7f006da 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java
@@ -208,7 +208,7 @@ class ImagePreprocessor {
DefaultExecutor executor = new DefaultExecutor();
// determine the angle of rotation required to make the text horizontal
- if (config.getApplyRotation() && hasPython(config)) {
+ if (config.isApplyRotation() && hasPython(config)) {
CommandLine commandLine = new CommandLine(getPythonPath(config));
String[] args = {"-W",
"ignore",
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
index f6c9d52..9ded5f3 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
@@ -181,7 +181,7 @@ public class TesseractOCRConfig implements Serializable {
// set parameters for ImageMagick
setEnableImageProcessing(
- getProp(props, "enableImageProcessing", getEnableImageProcessing()));
+ getProp(props, "enableImageProcessing", isEnableImageProcessing()));
setImageMagickPath(
getProp(props, "ImageMagickPath", getImageMagickPath()));
setDensity(
@@ -195,7 +195,7 @@ public class TesseractOCRConfig implements Serializable {
setResize(
getProp(props, "resize", getResize()));
setApplyRotation(
- getProp(props, "applyRotation", getApplyRotation()));
+ getProp(props, "applyRotation", isApplyRotation()));
setPythonPath(
getProp(props, "pythonPath", getPythonPath()));
@@ -330,7 +330,7 @@ public class TesseractOCRConfig implements Serializable {
*
* @return whether or not to maintain interword spacing.
*/
- public boolean getPreserveInterwordSpacing() {
+ public boolean isPreserveInterwordSpacing() {
return preserveInterwordSpacing;
}
/**
@@ -414,7 +414,7 @@ public class TesseractOCRConfig implements Serializable {
* @return image processing is enabled or not
* @see #setEnableImageProcessing(boolean)
*/
- public boolean getEnableImageProcessing() {
+ public boolean isEnableImageProcessing() {
return enableImageProcessing;
}
@@ -572,11 +572,12 @@ public class TesseractOCRConfig implements Serializable {
public String getPythonPath() {
return pythonPath;
}
+
/**
* @return Whether or not a rotation value should be calculated and passed to ImageMagick before performing OCR.
* (Requires that Python is installed).
*/
- public boolean getApplyRotation() {
+ public boolean isApplyRotation() {
return this.applyRotation;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
index 09afd9f..28fb5b8 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
@@ -238,7 +238,7 @@ public class TesseractOCRParser extends AbstractParser implements Initializable
if (size >= config.getMinFileSizeToOcr() && size <= config.getMaxFileSizeToOcr()) {
// Process image
- if (config.getEnableImageProcessing()) {
+ if (config.isEnableImageProcessing()) {
if (! ImagePreprocessor.hasImageMagick(config)) {
LOG.warn("User has selected to preprocess images, but I can't find ImageMagick." +
"Backing off to original file.");
@@ -339,7 +339,7 @@ public class TesseractOCRParser extends AbstractParser implements Initializable
cmd.addAll(Arrays.asList(
"-c", "page_separator=" + config.getPageSeparator(),
"-c",
- (config.getPreserveInterwordSpacing())? "preserve_interword_spaces=1" : "preserve_interword_spaces=0",
+ (config.isPreserveInterwordSpacing())? "preserve_interword_spaces=1" : "preserve_interword_spaces=0",
config.getOutputType().name().toLowerCase(Locale.US)
));
LOG.debug("Tesseract command: " + String.join(" ", cmd));
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRConfigTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRConfigTest.java
index f34ade2..530e1a3 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRConfigTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRConfigTest.java
@@ -47,7 +47,7 @@ public class TesseractOCRConfigTest extends TikaTest {
assertEquals("Invalid default colorpsace value", "gray" , config.getColorspace());
assertEquals("Invalid default filter value", "triangle" , config.getFilter());
assertEquals("Invalid default resize value", 900 , config.getResize());
- assertEquals("Invalid default applyRotation value", false, config.getApplyRotation());
+ assertEquals("Invalid default applyRotation value", false, config.isApplyRotation());
}
@Test
@@ -68,7 +68,7 @@ public class TesseractOCRConfigTest extends TikaTest {
assertEquals("Invalid overridden depth value", 8 , config.getDepth());
assertEquals("Invalid overridden filter value", "box" , config.getFilter());
assertEquals("Invalid overridden resize value", 300 , config.getResize());
- assertEquals("Invalid default applyRotation value", false, config.getApplyRotation());
+ assertEquals("Invalid default applyRotation value", false, config.isApplyRotation());
}
@Test
@@ -91,7 +91,7 @@ public class TesseractOCRConfigTest extends TikaTest {
assertEquals("Invalid overridden depth value", 8 , config.getDepth());
assertEquals("Invalid overridden filter value", "box" , config.getFilter());
assertEquals("Invalid overridden resize value", 300 , config.getResize());
- assertEquals("Invalid overridden applyRotation value", true, config.getApplyRotation());
+ assertEquals("Invalid overridden applyRotation value", true, config.isApplyRotation());
}
@Test
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
index 8c68fee..f91e046 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
@@ -18,11 +18,9 @@ package org.apache.tika.parser.ocr;
import org.apache.tika.TikaTest;
import org.apache.tika.config.TikaConfig;
-import org.apache.tika.metadata.HttpHeaders;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
-import org.apache.tika.parser.CompositeParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.external.ExternalParser;
@@ -152,7 +150,7 @@ public class TesseractOCRParserTest extends TikaTest {
Assert.assertEquals(241, tesseractOCRConfig.getTimeout());
Assert.assertEquals(TesseractOCRConfig.OUTPUT_TYPE.HOCR, tesseractOCRConfig.getOutputType());
Assert.assertEquals("ceb", tesseractOCRConfig.getLanguage());
- Assert.assertEquals(false, tesseractOCRConfig.getApplyRotation());
+ Assert.assertEquals(false, tesseractOCRConfig.isApplyRotation());
assertContains("myspecial", tesseractOCRConfig.getTesseractPath());
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
index 38d3026..f60e53c 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
@@ -403,7 +403,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
}
void handleCatchableIOE(IOException e) throws IOException {
- if (config.getCatchIntermediateIOExceptions()) {
+ if (config.isCatchIntermediateIOExceptions()) {
if (e.getCause() instanceof SAXException && e.getCause().getMessage() != null &&
e.getCause().getMessage().contains("Your document contained more than")) {
//TODO -- is there a cleaner way of checking for:
@@ -498,7 +498,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
handleWidget((PDAnnotationWidget)annotation);
}
// TODO: remove once PDFBOX-1143 is fixed:
- if (config.getExtractAnnotationText()) {
+ if (config.isExtractAnnotationText()) {
PDActionURI uri = getActionURI(annotation);
if (uri != null) {
String link = uri.getURI();
@@ -567,7 +567,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
unmappedUnicodeCharsPerPage = 0;
}
- if (config.getExtractFontNames()) {
+ if (config.isExtractFontNames()) {
for (COSName n : page.getResources().getFontNames()) {
PDFont font = page.getResources().getFont(n);
@@ -619,7 +619,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
private void handleDestinationOrAction(PDDestinationOrAction action,
ActionTrigger actionTrigger) throws IOException, SAXException, TikaException {
- if (action == null || ! config.getExtractActions()) {
+ if (action == null || ! config.isExtractActions()) {
return;
}
AttributesImpl attributes = new AttributesImpl();
@@ -677,7 +677,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
protected void endDocument(PDDocument pdf) throws IOException {
try {
// Extract text for any bookmarks:
- if(config.getExtractBookmarksText()) {
+ if(config.isExtractBookmarksText()) {
extractBookmarkText();
}
@@ -690,7 +690,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
extractXMPXFA(pdf, metadata, context);
//extract acroform data at end of doc
- if (config.getExtractAcroFormContent() == true) {
+ if (config.isExtractAcroFormContent() == true) {
try {
extractAcroForm(pdf);
} catch (IOException e) {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java
index 2e90243..6a9f402 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java
@@ -45,15 +45,11 @@ import org.apache.tika.exception.TikaMemoryLimitException;
import org.apache.tika.exception.ZeroByteFileException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
-import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
import org.apache.tika.io.BoundedInputStream;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.parser.EmptyParser;
import org.apache.tika.parser.ParseContext;
-import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.RecursiveParserWrapper;
import org.apache.tika.sax.EmbeddedContentHandler;
import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.SAXException;
@@ -117,7 +113,7 @@ class ImageGraphicsEngine extends PDFGraphicsStreamEngine {
this.xhtml = xhtml;
this.parentMetadata = parentMetadata;
this.parseContext = parseContext;
- this.extractInlineImageMetadataOnly = pdfParserConfig.getExtractInlineImageMetadataOnly();
+ this.extractInlineImageMetadataOnly = pdfParserConfig.isExtractInlineImageMetadataOnly();
}
void run() throws IOException {
@@ -164,7 +160,7 @@ class ImageGraphicsEngine extends PDFGraphicsStreamEngine {
PDImageXObject xobject = (PDImageXObject) pdImage;
Integer cachedNumber = processedInlineImages.get(xobject.getCOSObject());
- if (cachedNumber != null && pdfParserConfig.getExtractUniqueInlineImagesOnly()) {
+ if (cachedNumber != null && pdfParserConfig.isExtractUniqueInlineImagesOnly()) {
// skip duplicate image
return;
}
@@ -380,7 +376,7 @@ class ImageGraphicsEngine extends PDFGraphicsStreamEngine {
}
void handleCatchableIOE(IOException e) throws IOException {
- if (pdfParserConfig.getCatchIntermediateIOExceptions()) {
+ if (pdfParserConfig.isCatchIntermediateIOExceptions()) {
if (e.getCause() instanceof SAXException && e.getCause().getMessage() != null &&
e.getCause().getMessage().contains("Your document contained more than")) {
//TODO -- is there a cleaner way of checking for:
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
index 572087d..6de2f17 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
@@ -51,7 +51,7 @@ class PDF2XHTML extends AbstractPDF2XHTML {
/**
* This keeps track of the pdf object ids for inline
* images that have been processed.
- * If {@link PDFParserConfig#getExtractUniqueInlineImagesOnly()
+ * If {@link PDFParserConfig#isExtractUniqueInlineImagesOnly()
* is true, this will be checked before extracting an embedded image.
* The integer keeps track of the inlineImageCounter for that image.
* This integer is used to identify images in the markup.
@@ -86,7 +86,7 @@ class PDF2XHTML extends AbstractPDF2XHTML {
// Extract text using a dummy Writer as we override the
// key methods to output to the given content
// handler.
- if (config.getDetectAngles()) {
+ if (config.isDetectAngles()) {
pdf2XHTML = new AngleDetectingPDF2XHTML(document, handler, context, metadata, config);
} else {
pdf2XHTML = new PDF2XHTML(document, handler, context, metadata, config);
@@ -147,8 +147,8 @@ class PDF2XHTML extends AbstractPDF2XHTML {
}
void extractImages(PDPage page) throws SAXException, IOException {
- if (config.getExtractInlineImages() == false
- && config.getExtractInlineImageMetadataOnly() == false) {
+ if (config.isExtractInlineImages() == false
+ && config.isExtractInlineImageMetadataOnly() == false) {
return;
}
@@ -158,7 +158,7 @@ class PDF2XHTML extends AbstractPDF2XHTML {
List<IOException> engineExceptions = engine.getExceptions();
if (engineExceptions.size() > 0) {
IOException first = engineExceptions.remove(0);
- if (config.getCatchIntermediateIOExceptions()) {
+ if (config.isCatchIntermediateIOExceptions()) {
exceptions.addAll(engineExceptions);
}
throw first;
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
index 6a26838..89ed18b 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
@@ -125,7 +125,7 @@ public class PDFParser extends AbstractParser implements Initializable {
throws IOException, SAXException, TikaException {
PDFParserConfig localConfig = context.get(PDFParserConfig.class, defaultConfig);
- if (localConfig.getSetKCMS()) {
+ if (localConfig.isSetKCMS()) {
System.setProperty("sun.java2d.cmm", "sun.java2d.cmm.kcms.KcmsServiceProvider");
}
@@ -162,7 +162,7 @@ public class PDFParser extends AbstractParser implements Initializable {
handleXFAOnly(pdfDocument, handler, metadata, context);
} else if (localConfig.getOcrStrategy().equals(PDFParserConfig.OCR_STRATEGY.OCR_ONLY)) {
OCR2XHTML.process(pdfDocument, handler, context, metadata, localConfig);
- } else if (hasMarkedContent && localConfig.getExtractMarkedContent()) {
+ } else if (hasMarkedContent && localConfig.isExtractMarkedContent()) {
PDFMarkedContent2XHTML.process(pdfDocument, handler, context, metadata, localConfig);
} else {
PDF2XHTML.process(pdfDocument, handler, context, metadata, localConfig);
@@ -361,7 +361,7 @@ public class PDFParser extends AbstractParser implements Initializable {
}
private boolean shouldHandleXFAOnly(boolean hasXFA, PDFParserConfig config) {
- return config.getIfXFAExtractOnlyXFA() && hasXFA;
+ return config.isIfXFAExtractOnlyXFA() && hasXFA;
}
private void handleXFAOnly(PDDocument pdDocument, ContentHandler handler,
@@ -390,8 +390,8 @@ public class PDFParser extends AbstractParser implements Initializable {
/**
* @see #setEnableAutoSpace(boolean)
*/
- public boolean getEnableAutoSpace() {
- return defaultConfig.getEnableAutoSpace();
+ public boolean isEnableAutoSpace() {
+ return defaultConfig.isEnableAutoSpace();
}
/**
@@ -410,8 +410,8 @@ public class PDFParser extends AbstractParser implements Initializable {
*
* @deprecated use {@link #getPDFParserConfig()}
*/
- public boolean getExtractAnnotationText() {
- return defaultConfig.getExtractAnnotationText();
+ public boolean isExtractAnnotationText() {
+ return defaultConfig.isExtractAnnotationText();
}
/**
@@ -426,8 +426,8 @@ public class PDFParser extends AbstractParser implements Initializable {
* @see #setSuppressDuplicateOverlappingText(boolean)
* @deprecated use {@link #getPDFParserConfig()}
*/
- public boolean getSuppressDuplicateOverlappingText() {
- return defaultConfig.getSuppressDuplicateOverlappingText();
+ public boolean isSuppressDuplicateOverlappingText() {
+ return defaultConfig.isSuppressDuplicateOverlappingText();
}
/**
@@ -448,8 +448,8 @@ public class PDFParser extends AbstractParser implements Initializable {
* @see #setSortByPosition(boolean)
* @deprecated use {@link #getPDFParserConfig()}
*/
- public boolean getSortByPosition() {
- return defaultConfig.getSortByPosition();
+ public boolean isSortByPosition() {
+ return defaultConfig.isSortByPosition();
}
/**
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
index 179e208..b031a72 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
@@ -24,8 +24,6 @@ import java.util.Properties;
import org.apache.pdfbox.rendering.ImageType;
import org.apache.pdfbox.text.PDFTextStripper;
-import org.apache.tika.config.Field;
-import org.apache.tika.exception.TikaConfigException;
/**
* Config for PDFParser.
@@ -193,40 +191,40 @@ public class PDFParserConfig implements Serializable {
}
}
setEnableAutoSpace(
- getBooleanProp(props.getProperty("enableAutoSpace"), getEnableAutoSpace()));
+ getBooleanProp(props.getProperty("enableAutoSpace"), isEnableAutoSpace()));
setSuppressDuplicateOverlappingText(
getBooleanProp(props.getProperty("suppressDuplicateOverlappingText"),
- getSuppressDuplicateOverlappingText()));
+ isSuppressDuplicateOverlappingText()));
setExtractAnnotationText(
getBooleanProp(props.getProperty("extractAnnotationText"),
- getExtractAnnotationText()));
+ isExtractAnnotationText()));
setSortByPosition(
getBooleanProp(props.getProperty("sortByPosition"),
- getSortByPosition()));
+ isSortByPosition()));
setExtractAcroFormContent(
getBooleanProp(props.getProperty("extractAcroFormContent"),
- getExtractAcroFormContent()));
+ isExtractAcroFormContent()));
setExtractBookmarksText(
getBooleanProp(props.getProperty("extractBookmarksText"),
- getExtractBookmarksText()));
+ isExtractBookmarksText()));
setExtractInlineImages(
getBooleanProp(props.getProperty("extractInlineImages"),
- getExtractInlineImages()));
+ isExtractInlineImages()));
setExtractUniqueInlineImagesOnly(
getBooleanProp(props.getProperty("extractUniqueInlineImagesOnly"),
- getExtractUniqueInlineImagesOnly()));
+ isExtractUniqueInlineImagesOnly()));
setExtractInlineImageMetadataOnly(
getBooleanProp(props.getProperty("extractInlineImageMetadataOnly"),
- getExtractInlineImageMetadataOnly())
+ isExtractInlineImageMetadataOnly())
);
setExtractFontNames(
getBooleanProp(props.getProperty("extractFontNames"),
- getExtractFontNames()));
+ isExtractFontNames()));
setIfXFAExtractOnlyXFA(
getBooleanProp(props.getProperty("ifXFAExtractOnlyXFA"),
- getIfXFAExtractOnlyXFA()));
+ isIfXFAExtractOnlyXFA()));
setCatchIntermediateIOExceptions(
getBooleanProp(props.getProperty("catchIntermediateIOExceptions"),
@@ -284,7 +282,7 @@ public class PDFParserConfig implements Serializable {
*
* @return whether or not to extract only inline image metadata and not render the images
*/
- boolean getExtractInlineImageMetadataOnly() {
+ boolean isExtractInlineImageMetadataOnly() {
return extractInlineImageMetadataOnly;
}
@@ -300,7 +298,7 @@ public class PDFParserConfig implements Serializable {
this.extractMarkedContent = extractMarkedContent;
}
- public boolean getExtractMarkedContent() {
+ public boolean isExtractMarkedContent() {
return extractMarkedContent;
}
@@ -310,8 +308,8 @@ public class PDFParserConfig implements Serializable {
* @param pdf2XHTML
*/
public void configure(PDF2XHTML pdf2XHTML) {
- pdf2XHTML.setSortByPosition(getSortByPosition());
- if (getEnableAutoSpace()) {
+ pdf2XHTML.setSortByPosition(isSortByPosition());
+ if (isEnableAutoSpace()) {
pdf2XHTML.setWordSeparator(" ");
} else {
pdf2XHTML.setWordSeparator("");
@@ -325,13 +323,13 @@ public class PDFParserConfig implements Serializable {
if (getDropThreshold() != null) {
pdf2XHTML.setDropThreshold(dropThreshold);
}
- pdf2XHTML.setSuppressDuplicateOverlappingText(getSuppressDuplicateOverlappingText());
+ pdf2XHTML.setSuppressDuplicateOverlappingText(isSuppressDuplicateOverlappingText());
}
/**
* @see #setExtractAcroFormContent(boolean)
*/
- public boolean getExtractAcroFormContent() {
+ public boolean isExtractAcroFormContent() {
return extractAcroFormContent;
}
@@ -351,7 +349,7 @@ public class PDFParserConfig implements Serializable {
* @see #setIfXFAExtractOnlyXFA(boolean)
* @return how to handle XFA data if it exists
*/
- public boolean getIfXFAExtractOnlyXFA() {
+ public boolean isIfXFAExtractOnlyXFA() {
return ifXFAExtractOnlyXFA;
}
@@ -369,7 +367,7 @@ public class PDFParserConfig implements Serializable {
/**
* @see #setExtractBookmarksText(boolean)
*/
- public boolean getExtractBookmarksText() {
+ public boolean isExtractBookmarksText() {
return extractBookmarksText;
}
@@ -391,13 +389,13 @@ public class PDFParserConfig implements Serializable {
this.extractFontNames = extractFontNames;
}
- public boolean getExtractFontNames() {
+ public boolean isExtractFontNames() {
return extractFontNames;
}
/**
* @see #setExtractInlineImages(boolean)
*/
- public boolean getExtractInlineImages() {
+ public boolean isExtractInlineImages() {
return extractInlineImages;
}
@@ -422,7 +420,7 @@ public class PDFParserConfig implements Serializable {
/**
* @see #setExtractUniqueInlineImagesOnly(boolean)
*/
- public boolean getExtractUniqueInlineImagesOnly() {
+ public boolean isExtractUniqueInlineImagesOnly() {
return extractUniqueInlineImagesOnly;
}
@@ -454,7 +452,7 @@ public class PDFParserConfig implements Serializable {
/**
* @see #setEnableAutoSpace(boolean)
*/
- public boolean getEnableAutoSpace() {
+ public boolean isEnableAutoSpace() {
return enableAutoSpace;
}
@@ -471,7 +469,7 @@ public class PDFParserConfig implements Serializable {
/**
* @see #setSuppressDuplicateOverlappingText(boolean)
*/
- public boolean getSuppressDuplicateOverlappingText() {
+ public boolean isSuppressDuplicateOverlappingText() {
return suppressDuplicateOverlappingText;
}
@@ -492,7 +490,7 @@ public class PDFParserConfig implements Serializable {
/**
* @see #setExtractAnnotationText(boolean)
*/
- public boolean getExtractAnnotationText() {
+ public boolean isExtractAnnotationText() {
return extractAnnotationText;
}
@@ -507,7 +505,7 @@ public class PDFParserConfig implements Serializable {
/**
* @see #setSortByPosition(boolean)
*/
- public boolean getSortByPosition() {
+ public boolean isSortByPosition() {
return sortByPosition;
}
@@ -576,20 +574,12 @@ public class PDFParserConfig implements Serializable {
/**
* See {@link #setCatchIntermediateIOExceptions(boolean)}
* @return whether or not to catch IOExceptions
- * @deprecated use {@link #getCatchIntermediateIOExceptions()}
*/
public boolean isCatchIntermediateIOExceptions() {
return catchIntermediateIOExceptions;
}
/**
- * See {@link #setCatchIntermediateIOExceptions(boolean)}
- * @return whether or not to catch IOExceptions
- */
- public boolean getCatchIntermediateIOExceptions() {
- return catchIntermediateIOExceptions;
- }
- /**
* The PDFBox parser will throw an IOException if there is
* a problem with a stream. If this is set to <code>true</code>,
* Tika's PDFParser will catch these exceptions and try to parse
@@ -766,7 +756,7 @@ public class PDFParserConfig implements Serializable {
* @see #setExtractActions(boolean)
* @return whether or not to extract PDActions
*/
- public boolean getExtractActions() {
+ public boolean isExtractActions() {
return extractActions;
}
@@ -813,7 +803,7 @@ public class PDFParserConfig implements Serializable {
this.setKCMS = setKCMS;
}
- public boolean getSetKCMS() {
+ public boolean isSetKCMS() {
return setKCMS;
}
@@ -841,7 +831,7 @@ public class PDFParserConfig implements Serializable {
this.detectAngles = detectAngles;
}
- public boolean getDetectAngles() {
+ public boolean isDetectAngles() {
return detectAngles;
}
@@ -852,49 +842,49 @@ public class PDFParserConfig implements Serializable {
PDFParserConfig config = (PDFParserConfig) o;
- if (getEnableAutoSpace() != config.getEnableAutoSpace()) return false;
- if (getSuppressDuplicateOverlappingText() != config.getSuppressDuplicateOverlappingText()) return false;
- if (getExtractAnnotationText() != config.getExtractAnnotationText()) return false;
- if (getSortByPosition() != config.getSortByPosition()) return false;
- if (getExtractAcroFormContent() != config.getExtractAcroFormContent()) return false;
- if (getExtractBookmarksText() != config.getExtractBookmarksText()) return false;
- if (getExtractInlineImages() != config.getExtractInlineImages()) return false;
- if (getExtractUniqueInlineImagesOnly() != config.getExtractUniqueInlineImagesOnly()) return false;
- if (getIfXFAExtractOnlyXFA() != config.getIfXFAExtractOnlyXFA()) return false;
+ if (isEnableAutoSpace() != config.isEnableAutoSpace()) return false;
+ if (isSuppressDuplicateOverlappingText() != config.isSuppressDuplicateOverlappingText()) return false;
+ if (isExtractAnnotationText() != config.isExtractAnnotationText()) return false;
+ if (isSortByPosition() != config.isSortByPosition()) return false;
+ if (isExtractAcroFormContent() != config.isExtractAcroFormContent()) return false;
+ if (isExtractBookmarksText() != config.isExtractBookmarksText()) return false;
+ if (isExtractInlineImages() != config.isExtractInlineImages()) return false;
+ if (isExtractUniqueInlineImagesOnly() != config.isExtractUniqueInlineImagesOnly()) return false;
+ if (isIfXFAExtractOnlyXFA() != config.isIfXFAExtractOnlyXFA()) return false;
if (getOcrDPI() != config.getOcrDPI()) return false;
- if (getCatchIntermediateIOExceptions() != config.getCatchIntermediateIOExceptions()) return false;
+ if (isCatchIntermediateIOExceptions() != config.isCatchIntermediateIOExceptions()) return false;
if (!getAverageCharTolerance().equals(config.getAverageCharTolerance())) return false;
if (!getSpacingTolerance().equals(config.getSpacingTolerance())) return false;
if (!getDropThreshold().equals(config.getDropThreshold())) return false;
if (!getOcrStrategy().equals(config.getOcrStrategy())) return false;
if (getOcrImageType() != config.getOcrImageType()) return false;
if (!getOcrImageFormatName().equals(config.getOcrImageFormatName())) return false;
- if (getExtractActions() != config.getExtractActions()) return false;
+ if (isExtractActions() != config.isExtractActions()) return false;
if (!getAccessChecker().equals(config.getAccessChecker())) return false;
return getMaxMainMemoryBytes() == config.getMaxMainMemoryBytes();
}
@Override
public int hashCode() {
- int result = (getEnableAutoSpace() ? 1 : 0);
- result = 31 * result + (getSuppressDuplicateOverlappingText() ? 1 : 0);
- result = 31 * result + (getExtractAnnotationText() ? 1 : 0);
- result = 31 * result + (getSortByPosition() ? 1 : 0);
- result = 31 * result + (getExtractAcroFormContent() ? 1 : 0);
- result = 31 * result + (getExtractBookmarksText() ? 1 : 0);
- result = 31 * result + (getExtractInlineImages() ? 1 : 0);
- result = 31 * result + (getExtractUniqueInlineImagesOnly() ? 1 : 0);
+ int result = (isEnableAutoSpace() ? 1 : 0);
+ result = 31 * result + (isSuppressDuplicateOverlappingText() ? 1 : 0);
+ result = 31 * result + (isExtractAnnotationText() ? 1 : 0);
+ result = 31 * result + (isSortByPosition() ? 1 : 0);
+ result = 31 * result + (isExtractAcroFormContent() ? 1 : 0);
+ result = 31 * result + (isExtractBookmarksText() ? 1 : 0);
+ result = 31 * result + (isExtractInlineImages() ? 1 : 0);
+ result = 31 * result + (isExtractUniqueInlineImagesOnly() ? 1 : 0);
result = 31 * result + getAverageCharTolerance().hashCode();
result = 31 * result + getSpacingTolerance().hashCode();
result = 31 * result + getDropThreshold().hashCode();
- result = 31 * result + (getIfXFAExtractOnlyXFA() ? 1 : 0);
+ result = 31 * result + (isIfXFAExtractOnlyXFA() ? 1 : 0);
result = 31 * result + ocrStrategy.hashCode();
result = 31 * result + getOcrDPI();
result = 31 * result + getOcrImageType().hashCode();
result = 31 * result + getOcrImageFormatName().hashCode();
result = 31 * result + getAccessChecker().hashCode();
- result = 31 * result + (getCatchIntermediateIOExceptions() ? 1 : 0);
- result = 31 * result + (getExtractActions() ? 1 : 0);
+ result = 31 * result + (isCatchIntermediateIOExceptions() ? 1 : 0);
+ result = 31 * result + (isExtractActions() ? 1 : 0);
result = 31 * result + Long.valueOf(getMaxMainMemoryBytes()).hashCode();
return result;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
index 798c419..f34129d 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -26,7 +26,6 @@ import static org.junit.Assert.fail;
import static org.junit.Assume.assumeTrue;
import java.io.InputStream;
-import java.nio.file.Path;
import java.util.Arrays;
import java.util.HashMap;
import java.util.HashSet;
@@ -47,10 +46,7 @@ import org.apache.tika.exception.AccessPermissionException;
import org.apache.tika.exception.EncryptedDocumentException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.exception.ZeroByteFileException;
-import org.apache.tika.extractor.ContainerExtractor;
import org.apache.tika.extractor.DocumentSelector;
-import org.apache.tika.extractor.ParserContainerExtractor;
-import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Font;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Office;
@@ -65,7 +61,6 @@ import org.apache.tika.parser.CompositeParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.PasswordProvider;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ContentHandlerDecorator;
import org.apache.tika.sax.RecursiveParserWrapperHandler;
@@ -1134,13 +1129,13 @@ public class PDFParserTest extends TikaTest {
assertTrue(pdfParser instanceof PDFParser);
PDFParserConfig pdfParserConfig = ((PDFParser)pdfParser).getPDFParserConfig();
assertEquals(new AccessChecker(true), pdfParserConfig.getAccessChecker());
- assertEquals(true, pdfParserConfig.getExtractInlineImages());
- assertEquals(false, pdfParserConfig.getExtractUniqueInlineImagesOnly());
+ assertEquals(true, pdfParserConfig.isExtractInlineImages());
+ assertEquals(false, pdfParserConfig.isExtractUniqueInlineImagesOnly());
assertEquals(314, pdfParserConfig.getOcrDPI());
assertEquals(2.1f, pdfParserConfig.getOcrImageQuality(), .01f);
assertEquals("jpeg", pdfParserConfig.getOcrImageFormatName());
assertEquals(524288000, pdfParserConfig.getMaxMainMemoryBytes());
- assertEquals(false, pdfParserConfig.getCatchIntermediateIOExceptions());
+ assertEquals(false, pdfParserConfig.isCatchIntermediateIOExceptions());
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java
index 3af8d35..c9202e3 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java
@@ -94,7 +94,7 @@ public class Icu4jEncodingDetector implements EncodingDetector {
this.stripMarkup = stripMarkup;
}
- public boolean getStripMarkup() {
+ public boolean isStripMarkup() {
return stripMarkup;
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xliff/XLZParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xliff/XLZParser.java
index b40be84..246b7f0 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xliff/XLZParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xliff/XLZParser.java
@@ -110,7 +110,7 @@ public class XLZParser extends AbstractParser {
}
}
- if (handler.getEndDocumentWasCalled()) {
+ if (handler.isEndDocumentWasCalled()) {
handler.reallyEndDocument();
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java
index 4d5c66b..8fdf7fb 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java
@@ -87,7 +87,7 @@ public class TikaEncodingDetectorTest extends AbstractTikaConfigTest {
assertTrue(detector instanceof CompositeEncodingDetector);
List<EncodingDetector> detectors = ((CompositeEncodingDetector) detector).getDetectors();
assertEquals(2, detectors.size());
- assertTrue(((Icu4jEncodingDetector) detectors.get(0)).getStripMarkup());
+ assertTrue(((Icu4jEncodingDetector) detectors.get(0)).isStripMarkup());
assertTrue(detectors.get(1) instanceof NonDetectingEncodingDetector);
}